logo
These leaked GPU prototypes make the RTX 5090 look like a toy

These leaked GPU prototypes make the RTX 5090 look like a toy

Yahoo12-02-2025

Nvidia's best graphics cards are notorious for being power-hungry beasts, but some freshly leaked prototypes show that the company had much bigger plans. Various engineering samples surfaced on the Chiphell forums, including a prototype of the RTX 4090 with not one, not two, but four 16-pin power connectors. Will such designs ever see the light of day?
The leaker shared pictures of board prototypes going all the way back to the GTX 10 series, with the latest GPU being the RTX 4090. However, the leaker claims that the RTX 5090 was also prototyped with up to four power connectors, although such a card wasn't among the pictured boards.
Still, let's be real: Four 16-pin power connectors is a pretty insane number. Looking at the AD102 prototype, which corresponds to the RTX 4090 model, we're seeing those four 16-pin connectors alongside a 45-phase power delivery. One 12VHPWR connector means a maximum 600-watt power consumption, so using four of those would've brought that figure up to 2,400 watts. That's more than even the most high-end gaming PC consumes right now, and more than any power supply could possibly handle.
A prototype like this implies that Nvidia may have tried to dream (much) bigger, which links up with various whispers of a possible Titan GPU. Such a card, which many leakers claim was actually made for the Ada Lovelace lineup and then never used, would've ramped up both the overall specs and the power consumption.
Would the RTX 4090 (or 5090) Titan use four 12VHPWR connectors, though? No way. The most we've ever seen in a consumer GPU were overclocked variants of Nvidia's flagships, made by the company's board partners, which sported two. It's hard to imagine any GPU requiring that much power, nor would it be viable. We've heard of many cases of the 12VHPWR burning up — even in the RTX 5090 — so adding three more is hardly practical.
Older GPU models were featured too, with slightly less extreme power configurations. The Ampere generation was well represented: There was the GA102 Ampere board with four 8-pin connectors, but also the GA104 with three. Ampere cards ended up using 12-pin connectors outside of the prototype stage, but clearly, Nvidia was toying around with different designs too.
Keep in mind that we can't take these prototypes at face value. They look legitimate, but they didn't come directly from Nvidia. Still, assuming these are all real, it's interesting to see that Nvidia may have tried to create a 2,400-watt GPU. Good thing those plans never came to fruition.

Orange background

Try Our AI Features

Explore what Daily8 AI can do for you:

Comments

No comments yet...

Related Articles

Jensen Huang Praised Tesla, Said Every Car Will Need Autonomous Capability—'It's Safer, It's More Convenient, It's 'More Fun To Drive'
Jensen Huang Praised Tesla, Said Every Car Will Need Autonomous Capability—'It's Safer, It's More Convenient, It's 'More Fun To Drive'

Yahoo

time40 minutes ago

  • Yahoo

Jensen Huang Praised Tesla, Said Every Car Will Need Autonomous Capability—'It's Safer, It's More Convenient, It's 'More Fun To Drive'

Elon Musk posted on X on Sunday a segment from a year-old Yahoo Finance interview with Nvidia (NASDAQ:NVDA) CEO Jensen Huang. The conversation touched on many interesting points, but the reason Musk posted it is because of Huang's take on self-driving cars that stood Miss: Hasbro, MGM, and Skechers trust this AI marketing firm — Huang called Tesla (NASDAQ:TSLA) 'far ahead in self-driving cars' and predicted that every automaker will need to follow suit. 'Every single car someday will have to have autonomous capability,' Huang said. 'It's safer, it's more convenient, it's more fun to drive.' He explained that training self-driving systems is evolving. Instead of using labeled images, companies now feed raw video into AI models. 'Now we just put video right into the car and let the car figure it out by itself,' he said. This shift mimics how large language models are trained and signals a move toward AIs that better understand the physical world. Huang praised Tesla's use of end-to-end generative AI in its Full Self-Driving system. 'It learns from watching video, surround video, and it learns about how to drive end-to-end,' he said. 'It's really revolutionary.' Trending: Invest where it hurts — and help millions heal:. Video-based AI requires enormous data and processing power, and Huang made clear that Nvidia is ready. 'The best way to teach these AIs how the physical world behaves is through video—just watching tons and tons and tons of videos,' he said. Beyond Tesla, Huang cited growing interest from other automakers and industries. He said biotech companies are building AI supercomputers to generate molecules for drug discovery, and that even cloud providers are being outpaced by new sectors jumping into generative AI. 'We now have a software and AI model that can understand and learn almost any language—the language of English, of images, of video, of chemicals, of protein, even physics,' Huang said. 'And to be able to generate almost anything.'While Huang praised Tesla's approach, not everyone in the financial world is fully on board with its near-term autonomous driving ambitions. Future Fund LLC Managing Director Gary Black recently voiced concern about investor expectations tied to Tesla's Robotaxi rollout. 'I have warned $TSLA investors numerous times not to get too far ahead of themselves on unsupervised autonomy, including again yesterday,' Black wrote on X on May 22. He expects the term 'supervised autonomy' to become more common as Tesla moves closer to launching its ride-hailing Robotaxi service in Austin, Texas. 'Which is a far cry from unsupervised autonomy that supports many investors' robotaxi valuation models,' he added. CEO Elon Musk has said Tesla plans to launch the Robotaxis by the end of June, starting with over 10 vehicles. He also noted the company would be 'very careful' with the first introduction of unsupervised full self-driving. Musk also dismissed the idea of working with ride-hailing company Uber Technologies (NYSE:UBER), hinting instead at a proprietary Tesla platform where owners could add or remove their vehicles from the fleet. Read Next:Can you guess how many retire with a $5,000,000 nest egg? .UNLOCKED: 5 NEW TRADES EVERY WEEK. Click now to get top trade ideas daily, plus unlimited access to cutting-edge tools and strategies to gain an edge in the markets. Get the latest stock analysis from Benzinga? APPLE (AAPL): Free Stock Analysis Report TESLA (TSLA): Free Stock Analysis Report This article Jensen Huang Praised Tesla, Said Every Car Will Need Autonomous Capability—'It's Safer, It's More Convenient, It's 'More Fun To Drive' originally appeared on © 2025 Benzinga does not provide investment advice. All rights reserved. Error in retrieving data Sign in to access your portfolio Error in retrieving data Error in retrieving data Error in retrieving data Error in retrieving data

Nvidia CEO Jensen Huang Just Delivered Incredible News for Amazon Investors
Nvidia CEO Jensen Huang Just Delivered Incredible News for Amazon Investors

Yahoo

timean hour ago

  • Yahoo

Nvidia CEO Jensen Huang Just Delivered Incredible News for Amazon Investors

Nvidia surpassed expectations for revenue and earnings in the 2026 fiscal first quarter. CEO Jensen Huang sees a future where generative AI is embedded into all everyday applications. Amazon is the largest global provider of cloud computing services and will benefit from developers bringing AI into their applications. 10 stocks we like better than Amazon › It's been a good week for shareholders of Nvidia (NASDAQ: NVDA). The market has been worried about the powerhouse artificial intelligence (AI) company, but management assuaged many fears about its future opportunities and its ability to thrive despite regulatory issues that are weighing on its financial statements. CEO Jensen Huang gave many positive updates, and they don't just bode well for Nvidia, but for the long-term potential of generative AI -- and more specifically, AI superstar Amazon (NASDAQ: AMZN). The market wasn't sure what to expect from Nvidia's latest earnings release. Although the semiconductor giant is the dominant chipmaker in the industry, there have been a few updates that some believe mar its investing thesis. The market was disturbed when Chinese AI platform DeepSeek came out earlier this year, making people question whether or not Nvidia's high-priced chips were really necessary for generative AI development. And some chip shipments have been disrupted by regulatory efforts to keep the U.S.'s best equipment out of China. But performance has continued swimmingly at Nvidia, and it just released another fabulous round of earnings for the 2026 fiscal first quarter (ended April 27). Revenue increased 69% year over year to $44.1 billion, better than the $43.3 billion analysts were expecting, and adjusted earnings per share (EPS) were $0.96, better than the $0.93 target from analysts. Including a one-time charge related to deliveries it couldn't ship due to regulations about what chips it could send to China, EPS was $0.81, still way ahead of $0.60 last year. But it's the long-term outlook that keeps Nvidia's investing thesis strong. On the earnings call, Huang said: "We know that AI is this incredible technology that's going to transform every industry from, of course, the way we do software to healthcare and financial services to retail to, I guess, every industry, transportation, manufacturing. And we're at the beginning of that." Nvidia is now addressing the demand that it has helped create. Its most advanced chips, Blackwell, are selling fast, and they're in high demand from its large cloud computing clients like Amazon and Microsoft, the two largest global cloud providers. Nvidia's chief financial officer, Colette Kress, said on the earnings call that Microsoft alone was already using tens of thousands of Blackwell GPUs, and Blackwell accounted for 70% of data center sales in the first quarter. The company is already working on its next generation of GPUs, with each iteration more powerful, to handle the breakneck speed of AI development. Blackwell Ultra is already rolling in the current quarter, and Nvidia is working on even more powerful chips that can handle the inference part of generative AI, where the greatest demand is right now. Huang's sentiments echoed what Amazon CEO Andy Jassy recently said about the future of generative AI: I spent a fair bit of time thinking several years out. And while it may be hard for some to fathom a world where virtually every app has generative AI infused in it -- with inference being a core building block just like compute, storage, and data base, and most companies having their own agents that accomplish various tasks and interact with one another -- this is the world we're thinking about all the time. And we continue to believe that this world will mostly be built on top of the cloud, with the largest portion of it on AWS. Amazon Web Services (AWS) is the largest cloud services provider in the world, with 30% of the market, according to Statista. It inks new deals with high-profile clients all the time, including Adobe, Uber Technologies, and Cisco Systems in the first quarter. It's investing more than $100 billion into its AI business this year to be prepared to handle demand. Since most of the generative AI app development happens on the cloud, Amazon will benefit from that shift, as long as it's ready with best-in-class capabilities. Jassy often describes what it looks like: There's a three-layer system, with developers building their own large language models (LLMs) at the bottom for the most powerful generative AI platforms, a middle layer where clients use Amazon's LLMs, and a top layer where small businesses can use ready-made solutions for less intensive needs. Amazon has literally thousands of features to meet every demand and budget. "Before this generation of AI, we thought AWS had the chance to ultimately be a multi-hundred-billion-dollar revenue run rate business," Jassy said. "We now think it could be even larger." Amazon is developing its own, cheaper chips for smaller clients looking for budget-friendly options, but it's also one of Nvidia's biggest clients, and it's going to maintain that relationship because it needs the chipmaker's best-in-class products for its own big clients. Huang and Jassy are on the same page in envisioning what the future is going to look like. Nvidia's strong results and investments in its product line are good news for Jassy and Amazon as they build out to benefit from the shift. Before you buy stock in Amazon, consider this: The Motley Fool Stock Advisor analyst team just identified what they believe are the for investors to buy now… and Amazon wasn't one of them. The 10 stocks that made the cut could produce monster returns in the coming years. Consider when Netflix made this list on December 17, 2004... if you invested $1,000 at the time of our recommendation, you'd have $651,049!* Or when Nvidia made this list on April 15, 2005... if you invested $1,000 at the time of our recommendation, you'd have $828,224!* Now, it's worth noting Stock Advisor's total average return is 979% — a market-crushing outperformance compared to 171% for the S&P 500. Don't miss out on the latest top 10 list, available when you join . See the 10 stocks » *Stock Advisor returns as of May 19, 2025 John Mackey, former CEO of Whole Foods Market, an Amazon subsidiary, is a member of The Motley Fool's board of directors. Jennifer Saibil has no position in any of the stocks mentioned. The Motley Fool has positions in and recommends Adobe, Amazon, Cisco Systems, Microsoft, Nvidia, and Uber Technologies. The Motley Fool recommends the following options: long January 2026 $395 calls on Microsoft and short January 2026 $405 calls on Microsoft. The Motley Fool has a disclosure policy. Nvidia CEO Jensen Huang Just Delivered Incredible News for Amazon Investors was originally published by The Motley Fool Error in retrieving data Sign in to access your portfolio Error in retrieving data Error in retrieving data Error in retrieving data Error in retrieving data

Big Tech Is Back in S&P 500 Driver's Seat as Profit Engines Hum
Big Tech Is Back in S&P 500 Driver's Seat as Profit Engines Hum

Yahoo

timean hour ago

  • Yahoo

Big Tech Is Back in S&P 500 Driver's Seat as Profit Engines Hum

(Bloomberg) -- The same technology giants that helped drag the S&P 500 to the brink of a bear market in April are giving the recovery in US equities some legs. Billionaire Steve Cohen Wants NY to Expand Taxpayer-Backed Ferry Where the Wild Children's Museums Are Now With Colorful Blocks, Tirana's Pyramid Represents a Changing Albania The Economic Benefits of Paying Workers to Move NYC Congestion Toll Brings In $216 Million in First Four Months Nvidia Corp. put a bow on a better-than-expected earnings season for Big Tech last week by delivering a strong outlook for revenue, despite US restrictions on sales of its chips in China. With Nvidia and Microsoft Corp. rallying back to the cusp of record highs, traders are betting the group is poised to lift the broader market. 'I feel really good about tech coming out of this earnings season,' said Brett Ewing, chief market strategist at First Franklin Financial Services. 'There's still more gas in this tank.' The S&P 500 Index is within 4% of its February record high with much of the rebound being fueled by easing tensions between the US and its trade partners, as well as Big Tech results that showed demand for things like cloud-computing services, software, electronic devices and digital advertising remain intact even as the threat of higher tariffs on sales lingers. Tesla Inc. is up 56% since the benchmark bottomed out on April 8, while Nvidia and Microsoft have gained 40% and 30%, respectively. As a result, a Bloomberg gauge of the so-called Magnificent Seven stocks — Nvidia, Microsoft, Tesla, Apple Inc., Alphabet Inc., Inc. and Meta Platforms Inc. — is outperforming the S&P 500 over the past eight weeks — a critical shift for the benchmark considering the group accounts for a third of the index. The cohort is responsible for nearly half of the S&P 500's 19% rally from the April bottom, according to data compiled by Bloomberg. Despite the strong performance, the group is still trailing the S&P 500 for the year — a rare occurrence in the past decade. Shares of Apple and Amazon, which face greater risks from tariffs due to products imported, are weighing the cohort down and lag the overall market. 'Buying the tech dip will be a theme throughout the year,' said Ewing. 'There's still a lot of money on the sidelines and it has to be put to work.' Recovery Risks Tariffs and other Trump policies remain a big market overhang. On Friday, the benchmark sank more than 1% after Trump accused China of violating an agreement with the US to ease tariffs and a news report that the US plans to place broader restrictions on the country's tech sector. The S&P 500 managed to recoup most of those losses by the end of the day. Another hurdle will be Big Tech's hefty valuations. Bloomberg's Magnificent Seven gauge is priced at 30 times projected profits, according to data compiled by Bloomberg. Meanwhile, the S&P 500 is trading at 21 times earnings projected over the next 12 months, up from a low of 18 times in April and well above the average of 18.6 times over the past decade. Barry Knapp, managing partner at Ironsides Macroeconomics, said he's wary of Big Tech's rich valuations even though the group looks attractive from a fundamental perspective. He's 'modestly underweight' the sector and has relatively more exposure to industrials, materials, energy and financials in anticipation of a capital spending recovery in the second half of the year. 'Being overweight on tech here borders on recklessness, because you would have such a huge proportion of your portfolio in this one sector, and that leaves you vulnerable,' Knapp said. Market Catalyst Truist Advisory Services' Keith Lerner, however, sees Big Tech leading the broader market higher in the last half of 2025 with spending on artificial intelligence computing continuing to climb. Meta Platforms raised its forecast for capital expenditures this year and Microsoft said it plans to increase spending in its next fiscal year, alleviating concerns that the companies might pull back on such outlays after two years of largesse. 'Our view is that earnings could still be maybe flatter but likely have less downside than what we would have thought heading into the earnings season,' said Lerner, who is Truist's co-chief investment officer and chief market strategist. The Magnificent Seven profit estimates in 2025 have stayed steady over the past two months. The group is projected to deliver profit growth of 15%, roughly in-line with analysts' expectations before the reporting season began in mid-April and twice the expansion projected for the S&P 500, according to data compiled by Bloomberg Intelligence. 'Investors are going to be drawn back toward these names with secular growth,' said Lerner. Tech 'could be that catalyst later on to actually see the market re-accelerate later in the year.' YouTube Is Swallowing TV Whole, and It's Coming for the Sitcom Millions of Americans Are Obsessed With This Japanese Barbecue Sauce Mark Zuckerberg Loves MAGA Now. Will MAGA Ever Love Him Back? Will Small Business Owners Knock Down Trump's Mighty Tariffs? Trump Considers Deporting Migrants to Rwanda After the UK Decides Not To ©2025 Bloomberg L.P. Error in retrieving data Sign in to access your portfolio Error in retrieving data Error in retrieving data Error in retrieving data Error in retrieving data

DOWNLOAD THE APP

Get Started Now: Download the App

Ready to dive into the world of global news and events? Download our app today from your preferred app store and start exploring.
app-storeplay-store